Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    square root of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Incremental
    0.46
    Kappa
    0.44
    Threshold
    0.43
    VAT
    0.43
    не
    0.43
    PSO
    0.43
    개
    0.43
    Units
    0.42
    RECT
    0.41
    Manage
    0.40
    POSITIVE LOGITS
     fueran
    0.42
    几十
    0.42
     몸
    0.40
    aryng
    0.40
    生气
    0.40
    ियों
    0.38
     diplom
    0.38
    㓩
    0.38
    aziz
    0.36
    ingly
    0.36
    Act Density 0.010%

    No Known Activations